1 files changed, 658 insertions, 159 deletions

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 69aee3dfb660..860f0b1032c6 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -5,7 +5,7 @@
  * Copyright (C) 2019 Western Digital Corporation or its affiliates.
  */
 #include <linux/module.h>
-#include <linux/fs.h>
+#include <linux/pagemap.h>
 #include <linux/magic.h>
 #include <linux/iomap.h>
 #include <linux/init.h>
@@ -20,18 +20,140 @@
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/crc32.h>
+#include <linux/task_io_accounting_ops.h>
 
 #include "zonefs.h"
 
-static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
-			      unsigned int flags, struct iomap *iomap,
-			      struct iomap *srcmap)
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+/*
+ * Manage the active zone count. Called with zi->i_truncate_mutex held.
+ */
+static void zonefs_account_active(struct inode *inode)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	lockdep_assert_held(&zi->i_truncate_mutex);
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+		return;
+
+	/*
+	 * If the zone is active, that is, if it is explicitly open or
+	 * partially written, check if it was already accounted as active.
+	 */
+	if ((zi->i_flags & ZONEFS_ZONE_OPEN) ||
+	    (zi->i_wpoffset > 0 && zi->i_wpoffset < zi->i_max_size)) {
+		if (!(zi->i_flags & ZONEFS_ZONE_ACTIVE)) {
+			zi->i_flags |= ZONEFS_ZONE_ACTIVE;
+			atomic_inc(&sbi->s_active_seq_files);
+		}
+		return;
+	}
+
+	/* The zone is not active. If it was, update the active count */
+	if (zi->i_flags & ZONEFS_ZONE_ACTIVE) {
+		zi->i_flags &= ~ZONEFS_ZONE_ACTIVE;
+		atomic_dec(&sbi->s_active_seq_files);
+	}
+}
+
+static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret;
+
+	lockdep_assert_held(&zi->i_truncate_mutex);
+
+	/*
+	 * With ZNS drives, closing an explicitly open zone that has not been
+	 * written will change the zone state to "closed", that is, the zone
+	 * will remain active. Since this can then cause failure of explicit
+	 * open operation on other zones if the drive active zone resources
+	 * are exceeded, make sure that the zone does not remain active by
+	 * resetting it.
+	 */
+	if (op == REQ_OP_ZONE_CLOSE && !zi->i_wpoffset)
+		op = REQ_OP_ZONE_RESET;
+
+	trace_zonefs_zone_mgmt(inode, op);
+	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
+			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
+	if (ret) {
+		zonefs_err(inode->i_sb,
+			   "Zone management operation %s at %llu failed %d\n",
+			   blk_op_str(op), zi->i_zsector, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	i_size_write(inode, isize);
+	/*
+	 * A full zone is no longer open/active and does not need
+	 * explicit closing.
+	 */
+	if (isize >= zi->i_max_size) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+
+		if (zi->i_flags & ZONEFS_ZONE_ACTIVE)
+			atomic_dec(&sbi->s_active_seq_files);
+		zi->i_flags &= ~(ZONEFS_ZONE_OPEN | ZONEFS_ZONE_ACTIVE);
+	}
+}
+
+static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
+				   loff_t length, unsigned int flags,
+				   struct iomap *iomap, struct iomap *srcmap)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	loff_t isize;
 
-	/* All I/Os should always be within the file maximum size */
+	/*
+	 * All blocks are always mapped below EOF. If reading past EOF,
+	 * act as if there is a hole up to the file maximum size.
+	 */
+	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		iomap->length = length;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	trace_zonefs_iomap_begin(inode, iomap);
+
+	return 0;
+}
+
+static const struct iomap_ops zonefs_read_iomap_ops = {
+	.iomap_begin	= zonefs_read_iomap_begin,
+};
+
+static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
+				    loff_t length, unsigned int flags,
+				    struct iomap *iomap, struct iomap *srcmap)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+
+	/* All write I/Os should always be within the file maximum size */
 	if (WARN_ON_ONCE(offset + length > zi->i_max_size))
 		return -EIO;
 
@@ -41,7 +163,7 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * operation.
 	 */
 	if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
-			 (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
+			 !(flags & IOMAP_DIRECT)))
 		return -EIO;
 
 	/*
@@ -50,46 +172,44 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * write pointer) and unwriten beyond.
 	 */
 	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
 	isize = i_size_read(inode);
-	if (offset >= isize)
+	if (iomap->offset >= isize) {
 		iomap->type = IOMAP_UNWRITTEN;
-	else
+		iomap->length = zi->i_max_size - iomap->offset;
+	} else {
 		iomap->type = IOMAP_MAPPED;
-	if (flags & IOMAP_WRITE)
-		length = zi->i_max_size - offset;
-	else
-		length = min(length, isize - offset);
+		iomap->length = isize - iomap->offset;
+	}
 	mutex_unlock(&zi->i_truncate_mutex);
 
-	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
-	iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
+	trace_zonefs_iomap_begin(inode, iomap);
 
 	return 0;
 }
 
-static const struct iomap_ops zonefs_iomap_ops = {
-	.iomap_begin	= zonefs_iomap_begin,
+static const struct iomap_ops zonefs_write_iomap_ops = {
+	.iomap_begin	= zonefs_write_iomap_begin,
 };
 
-static int zonefs_readpage(struct file *unused, struct page *page)
+static int zonefs_read_folio(struct file *unused, struct folio *folio)
 {
-	return iomap_readpage(page, &zonefs_iomap_ops);
+	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
 }
 
-static int zonefs_readpages(struct file *unused, struct address_space *mapping,
-			    struct list_head *pages, unsigned int nr_pages)
+static void zonefs_readahead(struct readahead_control *rac)
 {
-	return iomap_readpages(mapping, pages, nr_pages, &zonefs_iomap_ops);
+	iomap_readahead(rac, &zonefs_read_iomap_ops);
 }
 
 /*
  * Map blocks for page writeback. This is used only on conventional zone files,
  * which implies that the page range can only be within the fixed inode size.
  */
-static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
-			     struct inode *inode, loff_t offset)
+static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
+				   struct inode *inode, loff_t offset)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
@@ -103,41 +223,50 @@ static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
 	    offset < wpc->iomap.offset + wpc->iomap.length)
 		return 0;
 
-	return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
-				  IOMAP_WRITE, &wpc->iomap, NULL);
+	return zonefs_write_iomap_begin(inode, offset, zi->i_max_size - offset,
+					IOMAP_WRITE, &wpc->iomap, NULL);
 }
 
 static const struct iomap_writeback_ops zonefs_writeback_ops = {
-	.map_blocks		= zonefs_map_blocks,
+	.map_blocks		= zonefs_write_map_blocks,
 };
 
-static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
+static int zonefs_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
 {
 	struct iomap_writepage_ctx wpc = { };
 
-	return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops);
+	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
 }
 
-static int zonefs_writepages(struct address_space *mapping,
-			     struct writeback_control *wbc)
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
 {
-	struct iomap_writepage_ctx wpc = { };
+	struct inode *inode = file_inode(swap_file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
-	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
+	if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+		zonefs_err(inode->i_sb,
+			   "swap file: not a conventional zone file\n");
+		return -EINVAL;
+	}
+
+	return iomap_swapfile_activate(sis, swap_file, span,
+				       &zonefs_read_iomap_ops);
 }
 
 static const struct address_space_operations zonefs_file_aops = {
-	.readpage		= zonefs_readpage,
-	.readpages		= zonefs_readpages,
-	.writepage		= zonefs_writepage,
+	.read_folio		= zonefs_read_folio,
+	.readahead		= zonefs_readahead,
 	.writepages		= zonefs_writepages,
-	.set_page_dirty		= iomap_set_page_dirty,
-	.releasepage		= iomap_releasepage,
-	.invalidatepage		= iomap_invalidatepage,
-	.migratepage		= iomap_migrate_page,
+	.dirty_folio		= filemap_dirty_folio,
+	.release_folio		= iomap_release_folio,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.direct_IO		= noop_direct_IO,
+	.swap_activate		= zonefs_swap_activate,
 };
 
 static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
@@ -178,7 +307,8 @@ static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
  * amount of readable data in the zone.
  */
 static loff_t zonefs_check_zone_condition(struct inode *inode,
-					  struct blk_zone *zone, bool warn)
+					  struct blk_zone *zone, bool warn,
+					  bool mount)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
@@ -196,13 +326,29 @@ static loff_t zonefs_check_zone_condition(struct inode *inode,
 		zone->wp = zone->start;
 		return 0;
 	case BLK_ZONE_COND_READONLY:
-		/* Do not allow writes in read-only zones */
+		/*
+		 * The write pointer of read-only zones is invalid. If such a
+		 * zone is found during mount, the file size cannot be retrieved
+		 * so we treat the zone as offline (mount == true case).
+		 * Otherwise, keep the file size as it was when last updated
+		 * so that the user can recover data. In both cases, writes are
+		 * always disabled for the zone.
+		 */
 		if (warn)
 			zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n",
 				    inode->i_ino);
 		inode->i_flags |= S_IMMUTABLE;
+		if (mount) {
+			zone->cond = BLK_ZONE_COND_OFFLINE;
+			inode->i_mode &= ~0777;
+			zone->wp = zone->start;
+			return 0;
+		}
 		inode->i_mode &= ~0222;
-		/* fallthrough */
+		return i_size_read(inode);
+	case BLK_ZONE_COND_FULL:
+		/* The write pointer of full zones is invalid. */
+		return zi->i_max_size;
 	default:
 		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
 			return zi->i_max_size;
@@ -231,7 +377,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * as there is no inconsistency between the inode size and the amount of
 	 * data writen in the zone (data_size).
 	 */
-	data_size = zonefs_check_zone_condition(inode, zone, true);
+	data_size = zonefs_check_zone_condition(inode, zone, true, false);
 	isize = i_size_read(inode);
 	if (zone->cond != BLK_ZONE_COND_OFFLINE &&
 	    zone->cond != BLK_ZONE_COND_READONLY &&
@@ -274,7 +420,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 		if (zone->cond != BLK_ZONE_COND_OFFLINE) {
 			zone->cond = BLK_ZONE_COND_OFFLINE;
 			data_size = zonefs_check_zone_condition(inode, zone,
-								false);
+								false, false);
 		}
 	} else if (zone->cond == BLK_ZONE_COND_READONLY ||
 		   sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) {
@@ -283,11 +429,22 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 		if (zone->cond != BLK_ZONE_COND_READONLY) {
 			zone->cond = BLK_ZONE_COND_READONLY;
 			data_size = zonefs_check_zone_condition(inode, zone,
-								false);
+								false, false);
 		}
 	}
 
 	/*
+	 * If the filesystem is mounted with the explicit-open mount option, we
+	 * need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
+	 * the read-only or offline condition, to avoid attempting an explicit
+	 * close of the zone when the inode file is closed.
+	 */
+	if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
+	    (zone->cond == BLK_ZONE_COND_OFFLINE ||
+	     zone->cond == BLK_ZONE_COND_READONLY))
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+
+	/*
 	 * If error=remount-ro was specified, any error result in remounting
 	 * the volume as read-only.
 	 */
@@ -301,8 +458,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
 	 * invalid data.
 	 */
 	zonefs_update_stats(inode, data_size);
-	i_size_write(inode, data_size);
+	zonefs_i_size_write(inode, data_size);
 	zi->i_wpoffset = data_size;
+	zonefs_account_active(inode);
 
 	return 0;
 }
@@ -314,22 +472,20 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
  * eventually correct the file size and zonefs inode write pointer offset
  * (which can be out of sync with the drive due to partial write failures).
  */
-static void zonefs_io_error(struct inode *inode, bool write)
+static void __zonefs_io_error(struct inode *inode, bool write)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	unsigned int noio_flag;
 	unsigned int nr_zones =
-		zi->i_max_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT);
+		zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT);
 	struct zonefs_ioerr_data err = {
 		.inode = inode,
 		.write = write,
 	};
 	int ret;
 
-	mutex_lock(&zi->i_truncate_mutex);
-
 	/*
 	 * Memory allocations in blkdev_report_zones() can trigger a memory
 	 * reclaim which may in turn cause a recursion into zonefs as well as
@@ -345,7 +501,14 @@ static void zonefs_io_error(struct inode *inode, bool write)
 		zonefs_err(sb, "Get inode %lu zone information failed %d\n",
 			   inode->i_ino, ret);
 	memalloc_noio_restore(noio_flag);
+}
+
+static void zonefs_io_error(struct inode *inode, bool write)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
+	mutex_lock(&zi->i_truncate_mutex);
+	__zonefs_io_error(inode, write);
 	mutex_unlock(&zi->i_truncate_mutex);
 }
 
@@ -353,7 +516,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	loff_t old_isize;
-	enum req_opf op;
+	enum req_op op;
 	int ret = 0;
 
 	/*
@@ -374,7 +537,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 	inode_dio_wait(inode);
 
 	/* Serialize against page faults */
-	down_write(&zi->i_mmap_sem);
+	filemap_invalidate_lock(inode->i_mapping);
 
 	/* Serialize against zonefs_iomap_begin() */
 	mutex_lock(&zi->i_truncate_mutex);
@@ -383,27 +546,43 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
 	if (isize == old_isize)
 		goto unlock;
 
-	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
-			       zi->i_max_size >> SECTOR_SHIFT, GFP_NOFS);
-	if (ret) {
-		zonefs_err(inode->i_sb,
-			   "Zone management operation at %llu failed %d",
-			   zi->i_zsector, ret);
+	ret = zonefs_zone_mgmt(inode, op);
+	if (ret)
 		goto unlock;
+
+	/*
+	 * If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
+	 * take care of open zones.
+	 */
+	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
+		/*
+		 * Truncating a zone to EMPTY or FULL is the equivalent of
+		 * closing the zone. For a truncation to 0, we need to
+		 * re-open the zone to ensure new writes can be processed.
+		 * For a truncation to the maximum file size, the zone is
+		 * closed and writes cannot be accepted anymore, so clear
+		 * the open flag.
+		 */
+		if (!isize)
+			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+		else
+			zi->i_flags &= ~ZONEFS_ZONE_OPEN;
 	}
 
 	zonefs_update_stats(inode, isize);
 	truncate_setsize(inode, isize);
 	zi->i_wpoffset = isize;
+	zonefs_account_active(inode);
 
 unlock:
 	mutex_unlock(&zi->i_truncate_mutex);
-	up_write(&zi->i_mmap_sem);
+	filemap_invalidate_unlock(inode->i_mapping);
 
 	return ret;
 }
 
-static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
+static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
+				struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
 	int ret;
@@ -411,7 +590,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	if (unlikely(IS_IMMUTABLE(inode)))
 		return -EPERM;
 
-	ret = setattr_prepare(dentry, iattr);
+	ret = setattr_prepare(&init_user_ns, dentry, iattr);
 	if (ret)
 		return ret;
 
@@ -428,7 +607,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	     !uid_eq(iattr->ia_uid, inode->i_uid)) ||
 	    ((iattr->ia_valid & ATTR_GID) &&
 	     !gid_eq(iattr->ia_gid, inode->i_gid))) {
-		ret = dquot_transfer(inode, iattr);
+		ret = dquot_transfer(mnt_userns, inode, iattr);
 		if (ret)
 			return ret;
 	}
@@ -439,7 +618,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 			return ret;
 	}
 
-	setattr_copy(inode, iattr);
+	setattr_copy(&init_user_ns, inode, iattr);
 
 	return 0;
 }
@@ -464,7 +643,7 @@ static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
 	if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV)
 		ret = file_write_and_wait_range(file, start, end);
 	if (!ret)
-		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev);
 
 	if (ret)
 		zonefs_io_error(inode, true);
@@ -472,18 +651,6 @@ static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
 	return ret;
 }
 
-static vm_fault_t zonefs_filemap_fault(struct vm_fault *vmf)
-{
-	struct zonefs_inode_info *zi = ZONEFS_I(file_inode(vmf->vma->vm_file));
-	vm_fault_t ret;
-
-	down_read(&zi->i_mmap_sem);
-	ret = filemap_fault(vmf);
-	up_read(&zi->i_mmap_sem);
-
-	return ret;
-}
-
 static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -504,16 +671,16 @@ static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 	file_update_time(vmf->vma->vm_file);
 
 	/* Serialize against truncates */
-	down_read(&zi->i_mmap_sem);
-	ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
-	up_read(&zi->i_mmap_sem);
+	filemap_invalidate_lock_shared(inode->i_mapping);
+	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
+	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
 static const struct vm_operations_struct zonefs_file_vm_ops = {
-	.fault		= zonefs_filemap_fault,
+	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= zonefs_filemap_page_mkwrite,
 };
@@ -570,7 +737,7 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
 		mutex_lock(&zi->i_truncate_mutex);
 		if (i_size_read(inode) < iocb->ki_pos + size) {
 			zonefs_update_stats(inode, iocb->ki_pos + size);
-			i_size_write(inode, iocb->ki_pos + size);
+			zonefs_i_size_write(inode, iocb->ki_pos + size);
 		}
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
@@ -582,6 +749,120 @@ static const struct iomap_dio_ops zonefs_write_dio_ops = {
 	.end_io			= zonefs_file_write_dio_end_io,
 };
 
+static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	unsigned int max = bdev_max_zone_append_sectors(bdev);
+	struct bio *bio;
+	ssize_t size;
+	int nr_pages;
+	ssize_t ret;
+
+	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
+	iov_iter_truncate(from, max);
+
+	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
+	if (!nr_pages)
+		return 0;
+
+	bio = bio_alloc(bdev, nr_pages,
+			REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE, GFP_NOFS);
+	bio->bi_iter.bi_sector = zi->i_zsector;
+	bio->bi_ioprio = iocb->ki_ioprio;
+	if (iocb_is_dsync(iocb))
+		bio->bi_opf |= REQ_FUA;
+
+	ret = bio_iov_iter_get_pages(bio, from);
+	if (unlikely(ret))
+		goto out_release;
+
+	size = bio->bi_iter.bi_size;
+	task_io_account_write(size);
+
+	if (iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(bio, iocb);
+
+	ret = submit_bio_wait(bio);
+
+	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+	trace_zonefs_file_dio_append(inode, size, ret);
+
+out_release:
+	bio_release_pages(bio, false);
+	bio_put(bio);
+
+	if (ret >= 0) {
+		iocb->ki_pos += size;
+		return size;
+	}
+
+	return ret;
+}
+
+/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+					loff_t count)
+{
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+	loff_t max_size = zi->i_max_size;
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		count = min(count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t count;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	if (iocb->ki_flags & IOCB_APPEND) {
+		if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+			return -EINVAL;
+		mutex_lock(&zi->i_truncate_mutex);
+		iocb->ki_pos = zi->i_wpoffset;
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+	count = zonefs_write_check_limits(file, iocb->ki_pos,
+					  iov_iter_count(from));
+	if (count < 0)
+		return count;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+
 /*
  * Handle direct writes. For sequential zone files, this is the only possible
  * write path. For these files, check that the user is issuing writes
@@ -597,15 +878,16 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
-	size_t count;
-	ssize_t ret;
+	bool sync = is_sync_kiocb(iocb);
+	bool append = false;
+	ssize_t ret, count;
 
 	/*
 	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
 	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
 	 * on the inode lock but the second goes through but is now unaligned).
 	 */
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) &&
+	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
@@ -616,12 +898,11 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
-	if (ret <= 0)
+	count = zonefs_write_checks(iocb, from);
+	if (count <= 0) {
+		ret = count;
 		goto inode_unlock;
-
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-	count = iov_iter_count(from);
+	}
 
 	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
 		ret = -EINVAL;
@@ -629,22 +910,35 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Enforce sequential writes (append only) in sequential zones */
-	mutex_lock(&zi->i_truncate_mutex);
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && iocb->ki_pos != zi->i_wpoffset) {
+	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
+		mutex_lock(&zi->i_truncate_mutex);
+		if (iocb->ki_pos != zi->i_wpoffset) {
+			mutex_unlock(&zi->i_truncate_mutex);
+			ret = -EINVAL;
+			goto inode_unlock;
+		}
 		mutex_unlock(&zi->i_truncate_mutex);
-		ret = -EINVAL;
-		goto inode_unlock;
+		append = sync;
 	}
-	mutex_unlock(&zi->i_truncate_mutex);
 
-	ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-			   &zonefs_write_dio_ops, is_sync_kiocb(iocb));
+	if (append)
+		ret = zonefs_file_dio_append(iocb, from);
+	else
+		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
+				   &zonefs_write_dio_ops, 0, NULL, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)
 			count = ret;
+
+		/*
+		 * Update the zone write pointer offset assuming the write
+		 * operation succeeded. If it did not, the error recovery path
+		 * will correct it. Also do active seq file accounting.
+		 */
 		mutex_lock(&zi->i_truncate_mutex);
 		zi->i_wpoffset += count;
+		zonefs_account_active(inode);
 		mutex_unlock(&zi->i_truncate_mutex);
 	}
 
@@ -675,13 +969,11 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
+	ret = zonefs_write_checks(iocb, from);
 	if (ret <= 0)
 		goto inode_unlock;
 
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
-	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
 	if (ret > 0)
 		iocb->ki_pos += ret;
 	else if (ret == -EIO)
@@ -709,8 +1001,11 @@ static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size)
 		return -EFBIG;
 
-	if (iocb->ki_flags & IOCB_DIRECT)
-		return zonefs_file_dio_write(iocb, from);
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ssize_t ret = zonefs_file_dio_write(iocb, from);
+		if (ret != -ENOTBLK)
+			return ret;
+	}
 
 	return zonefs_file_buffered_write(iocb, from);
 }
@@ -771,8 +1066,8 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			goto inode_unlock;
 		}
 		file_accessed(iocb->ki_filp);
-		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, is_sync_kiocb(iocb));
+		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
+				   &zonefs_read_dio_ops, 0, NULL, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)
@@ -785,8 +1080,144 @@ inode_unlock:
 	return ret;
 }
 
+/*
+ * Write open accounting is done only for sequential files.
+ */
+static inline bool zonefs_seq_file_need_wro(struct inode *inode,
+					    struct file *file)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+		return false;
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return false;
+
+	return true;
+}
+
+static int zonefs_seq_file_write_open(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	if (!zi->i_wr_refcnt) {
+		struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
+		unsigned int wro = atomic_inc_return(&sbi->s_wro_seq_files);
+
+		if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+
+			if (sbi->s_max_wro_seq_files
+			    && wro > sbi->s_max_wro_seq_files) {
+				atomic_dec(&sbi->s_wro_seq_files);
+				ret = -EBUSY;
+				goto unlock;
+			}
+
+			if (i_size_read(inode) < zi->i_max_size) {
+				ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
+				if (ret) {
+					atomic_dec(&sbi->s_wro_seq_files);
+					goto unlock;
+				}
+				zi->i_flags |= ZONEFS_ZONE_OPEN;
+				zonefs_account_active(inode);
+			}
+		}
+	}
+
+	zi->i_wr_refcnt++;
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return ret;
+}
+
+static int zonefs_file_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = generic_file_open(inode, file);
+	if (ret)
+		return ret;
+
+	if (zonefs_seq_file_need_wro(inode, file))
+		return zonefs_seq_file_write_open(inode);
+
+	return 0;
+}
+
+static void zonefs_seq_file_write_close(struct inode *inode)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	int ret = 0;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	zi->i_wr_refcnt--;
+	if (zi->i_wr_refcnt)
+		goto unlock;
+
+	/*
+	 * The file zone may not be open anymore (e.g. the file was truncated to
+	 * its maximum size or it was fully written). For this case, we only
+	 * need to decrement the write open count.
+	 */
+	if (zi->i_flags & ZONEFS_ZONE_OPEN) {
+		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+		if (ret) {
+			__zonefs_io_error(inode, false);
+			/*
+			 * Leaving zones explicitly open may lead to a state
+			 * where most zones cannot be written (zone resources
+			 * exhausted). So take preventive action by remounting
+			 * read-only.
+			 */
+			if (zi->i_flags & ZONEFS_ZONE_OPEN &&
+			    !(sb->s_flags & SB_RDONLY)) {
+				zonefs_warn(sb,
+					"closing zone at %llu failed %d\n",
+					zi->i_zsector, ret);
+				zonefs_warn(sb,
+					"remounting filesystem read-only\n");
+				sb->s_flags |= SB_RDONLY;
+			}
+			goto unlock;
+		}
+
+		zi->i_flags &= ~ZONEFS_ZONE_OPEN;
+		zonefs_account_active(inode);
+	}
+
+	atomic_dec(&sbi->s_wro_seq_files);
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+}
+
+static int zonefs_file_release(struct inode *inode, struct file *file)
+{
+	/*
+	 * If we explicitly open a zone we must close it again as well, but the
+	 * zone management operation can fail (either due to an IO error or as
+	 * the zone has gone offline or read-only). Make sure we don't fail the
+	 * close(2) for user-space.
+	 */
+	if (zonefs_seq_file_need_wro(inode, file))
+		zonefs_seq_file_write_close(inode);
+
+	return 0;
+}
+
 static const struct file_operations zonefs_file_operations = {
-	.open		= generic_file_open,
+	.open		= zonefs_file_open,
+	.release	= zonefs_file_release,
 	.fsync		= zonefs_file_fsync,
 	.mmap		= zonefs_file_mmap,
 	.llseek		= zonefs_file_llseek,
@@ -794,7 +1225,7 @@ static const struct file_operations zonefs_file_operations = {
 	.write_iter	= zonefs_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-	.iopoll		= iomap_dio_iopoll,
+	.iopoll		= iocb_bio_iopoll,
 };
 
 static struct kmem_cache *zonefs_inode_cachep;
@@ -803,13 +1234,14 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb)
 {
 	struct zonefs_inode_info *zi;
 
-	zi = kmem_cache_alloc(zonefs_inode_cachep, GFP_KERNEL);
+	zi = alloc_inode_sb(sb, zonefs_inode_cachep, GFP_KERNEL);
 	if (!zi)
 		return NULL;
 
 	inode_init_once(&zi->i_vnode);
 	mutex_init(&zi->i_truncate_mutex);
-	init_rwsem(&zi->i_mmap_sem);
+	zi->i_wr_refcnt = 0;
+	zi->i_flags = 0;
 
 	return &zi->i_vnode;
 }
@@ -827,7 +1259,6 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct super_block *sb = dentry->d_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	enum zonefs_ztype t;
-	u64 fsid;
 
 	buf->f_type = ZONEFS_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
@@ -850,17 +1281,14 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	spin_unlock(&sbi->s_lock);
 
-	fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
-		le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
-	buf->f_fsid.val[0] = (u32)fsid;
-	buf->f_fsid.val[1] = (u32)(fsid >> 32);
+	buf->f_fsid = uuid_to_fsid(sbi->s_uuid.b);
 
 	return 0;
 }
 
 enum {
 	Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
-	Opt_err,
+	Opt_explicit_open, Opt_err,
 };
 
 static const match_table_t tokens = {
@@ -868,6 +1296,7 @@ static const match_table_t tokens = {
 	{ Opt_errors_zro,	"errors=zone-ro"},
 	{ Opt_errors_zol,	"errors=zone-offline"},
 	{ Opt_errors_repair,	"errors=repair"},
+	{ Opt_explicit_open,	"explicit-open" },
 	{ Opt_err,		NULL}
 };
 
@@ -904,6 +1333,9 @@ static int zonefs_parse_options(struct super_block *sb, char *options)
 			sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
 			sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
 			break;
+		case Opt_explicit_open:
+			sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -953,34 +1385,37 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
 {
 	struct super_block *sb = parent->i_sb;
 
-	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
-	inode_init_owner(inode, parent, S_IFDIR | 0555);
+	inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
+	inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
 	inode->i_op = &zonefs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	set_nlink(inode, 2);
 	inc_nlink(parent);
 }
 
-static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
-				   enum zonefs_ztype type)
+static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
+				  enum zonefs_ztype type)
 {
 	struct super_block *sb = inode->i_sb;
 	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	int ret = 0;
 
 	inode->i_ino = zone->start >> sbi->s_zone_sectors_shift;
 	inode->i_mode = S_IFREG | sbi->s_perm;
 
 	zi->i_ztype = type;
 	zi->i_zsector = zone->start;
+	zi->i_zone_size = zone->len << SECTOR_SHIFT;
+
 	zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE,
-			       zone->len << SECTOR_SHIFT);
-	zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true);
+			       zone->capacity << SECTOR_SHIFT);
+	zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true);
 
 	inode->i_uid = sbi->s_uid;
 	inode->i_gid = sbi->s_gid;
 	inode->i_size = zi->i_wpoffset;
-	inode->i_blocks = zone->len;
+	inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT;
 
 	inode->i_op = &zonefs_file_inode_operations;
 	inode->i_fop = &zonefs_file_operations;
@@ -989,6 +1424,29 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
 	sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes);
 	sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits;
 	sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits;
+
+	mutex_lock(&zi->i_truncate_mutex);
+
+	/*
+	 * For sequential zones, make sure that any open zone is closed first
+	 * to ensure that the initial number of open zones is 0, in sync with
+	 * the open zone accounting done when the mount option
+	 * ZONEFS_MNTOPT_EXPLICIT_OPEN is used.
+	 */
+	if (type == ZONEFS_ZTYPE_SEQ &&
+	    (zone->cond == BLK_ZONE_COND_IMP_OPEN ||
+	     zone->cond == BLK_ZONE_COND_EXP_OPEN)) {
+		ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
+		if (ret)
+			goto unlock;
+	}
+
+	zonefs_account_active(inode);
+
+unlock:
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	return ret;
 }
 
 static struct dentry *zonefs_create_inode(struct dentry *parent,
@@ -998,6 +1456,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent,
 	struct inode *dir = d_inode(parent);
 	struct dentry *dentry;
 	struct inode *inode;
+	int ret;
 
 	dentry = d_alloc_name(parent, name);
 	if (!dentry)
@@ -1008,10 +1467,16 @@ static struct dentry *zonefs_create_inode(struct dentry *parent,
 		goto dput;
 
 	inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
-	if (zone)
-		zonefs_init_file_inode(inode, zone, type);
-	else
+	if (zone) {
+		ret = zonefs_init_file_inode(inode, zone, type);
+		if (ret) {
+			iput(inode);
+			goto dput;
+		}
+	} else {
 		zonefs_init_dir_inode(dir, inode, type);
+	}
+
 	d_add(dentry, inode);
 	dir->i_size++;
 
@@ -1042,7 +1507,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 	char *file_name;
 	struct dentry *dir;
 	unsigned int n = 0;
-	int ret = -ENOMEM;
+	int ret;
 
 	/* If the group is empty, there is nothing to do */
 	if (!zd->nr_zones[type])
@@ -1058,13 +1523,15 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 		zgroup_name = "seq";
 
 	dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type);
-	if (!dir)
+	if (!dir) {
+		ret = -ENOMEM;
 		goto free;
+	}
 
 	/*
 	 * The first zone contains the super block: skip it.
 	 */
-	end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
+	end = zd->zones + bdev_nr_zones(sb->s_bdev);
 	for (zone = &zd->zones[1]; zone < end; zone = next) {
 
 		next = zone + 1;
@@ -1085,20 +1552,28 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
 				if (zonefs_zone_type(next) != type)
 					break;
 				zone->len += next->len;
+				zone->capacity += next->capacity;
 				if (next->cond == BLK_ZONE_COND_READONLY &&
 				    zone->cond != BLK_ZONE_COND_OFFLINE)
 					zone->cond = BLK_ZONE_COND_READONLY;
 				else if (next->cond == BLK_ZONE_COND_OFFLINE)
 					zone->cond = BLK_ZONE_COND_OFFLINE;
 			}
+			if (zone->capacity != zone->len) {
+				zonefs_err(sb, "Invalid conventional zone capacity\n");
+				ret = -EINVAL;
+				goto free;
+			}
 		}
 
 		/*
 		 * Use the file number within its group as file name.
 		 */
 		snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n);
-		if (!zonefs_create_inode(dir, file_name, zone, type))
+		if (!zonefs_create_inode(dir, file_name, zone, type)) {
+			ret = -ENOMEM;
 			goto free;
+		}
 
 		n++;
 	}
@@ -1151,8 +1626,8 @@ static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
 	struct block_device *bdev = zd->sb->s_bdev;
 	int ret;
 
-	zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk),
-			     sizeof(struct blk_zone), GFP_KERNEL);
+	zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
+			     GFP_KERNEL);
 	if (!zd->zones)
 		return -ENOMEM;
 
@@ -1164,9 +1639,9 @@ static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
 		return ret;
 	}
 
-	if (ret != blkdev_nr_zones(bdev->bd_disk)) {
+	if (ret != bdev_nr_zones(bdev)) {
 		zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
-			   ret, blkdev_nr_zones(bdev->bd_disk));
+			   ret, bdev_nr_zones(bdev));
 		return -EIO;
 	}
 
@@ -1195,21 +1670,19 @@ static int zonefs_read_super(struct super_block *sb)
 	if (!page)
 		return -ENOMEM;
 
-	bio_init(&bio, &bio_vec, 1);
+	bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ);
 	bio.bi_iter.bi_sector = 0;
-	bio.bi_opf = REQ_OP_READ;
-	bio_set_dev(&bio, sb->s_bdev);
 	bio_add_page(&bio, page, PAGE_SIZE, 0);
 
 	ret = submit_bio_wait(&bio);
 	if (ret)
 		goto free_page;
 
-	super = kmap(page);
+	super = page_address(page);
 
 	ret = -EINVAL;
 	if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC)
-		goto unmap;
+		goto free_page;
 
 	stored_crc = le32_to_cpu(super->s_crc);
 	super->s_crc = 0;
@@ -1217,14 +1690,14 @@ static int zonefs_read_super(struct super_block *sb)
 	if (crc != stored_crc) {
 		zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)",
 			   crc, stored_crc);
-		goto unmap;
+		goto free_page;
 	}
 
 	sbi->s_features = le64_to_cpu(super->s_features);
 	if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) {
 		zonefs_err(sb, "Unknown features set 0x%llx\n",
 			   sbi->s_features);
-		goto unmap;
+		goto free_page;
 	}
 
 	if (sbi->s_features & ZONEFS_F_UID) {
@@ -1232,7 +1705,7 @@ static int zonefs_read_super(struct super_block *sb)
 				       le32_to_cpu(super->s_uid));
 		if (!uid_valid(sbi->s_uid)) {
 			zonefs_err(sb, "Invalid UID feature\n");
-			goto unmap;
+			goto free_page;
 		}
 	}
 
@@ -1241,7 +1714,7 @@ static int zonefs_read_super(struct super_block *sb)
 				       le32_to_cpu(super->s_gid));
 		if (!gid_valid(sbi->s_gid)) {
 			zonefs_err(sb, "Invalid GID feature\n");
-			goto unmap;
+			goto free_page;
 		}
 	}
 
@@ -1250,14 +1723,12 @@ static int zonefs_read_super(struct super_block *sb)
 
 	if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) {
 		zonefs_err(sb, "Reserved area is being used\n");
-		goto unmap;
+		goto free_page;
 	}
 
-	uuid_copy(&sbi->s_uuid, (uuid_t *)super->s_uuid);
+	import_uuid(&sbi->s_uuid, super->s_uuid);
 	ret = 0;
 
-unmap:
-	kunmap(page);
 free_page:
 	__free_page(page);
 
@@ -1300,18 +1771,22 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran	= 1;
 
 	/*
-	 * The block size is set to the device physical sector size to ensure
-	 * that write operations on 512e devices (512B logical block and 4KB
-	 * physical block) are always aligned to the device physical blocks,
-	 * as mandated by the ZBC/ZAC specifications.
+	 * The block size is set to the device zone write granularity to ensure
+	 * that write operations are always aligned according to the device
+	 * interface constraints.
 	 */
-	sb_set_blocksize(sb, bdev_physical_block_size(sb->s_bdev));
+	sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev));
 	sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev));
 	sbi->s_uid = GLOBAL_ROOT_UID;
 	sbi->s_gid = GLOBAL_ROOT_GID;
 	sbi->s_perm = 0640;
 	sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
 
+	atomic_set(&sbi->s_wro_seq_files, 0);
+	sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev);
+	atomic_set(&sbi->s_active_seq_files, 0);
+	sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev);
+
 	ret = zonefs_read_super(sb);
 	if (ret)
 		return ret;
@@ -1326,8 +1801,19 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	if (ret)
 		goto cleanup;
 
-	zonefs_info(sb, "Mounting %u zones",
-		    blkdev_nr_zones(sb->s_bdev->bd_disk));
+	ret = zonefs_sysfs_register(sb);
+	if (ret)
+		goto cleanup;
+
+	zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
+
+	if (!sbi->s_max_wro_seq_files &&
+	    !sbi->s_max_active_seq_files &&
+	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+		zonefs_info(sb,
+			"No open and active zone limits. Ignoring explicit_open mount option\n");
+		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
+	}
 
 	/* Create root directory inode */
 	ret = -ENOMEM;
@@ -1335,7 +1821,7 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	if (!inode)
 		goto cleanup;
 
-	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
+	inode->i_ino = bdev_nr_zones(sb->s_bdev);
 	inode->i_mode = S_IFDIR | 0555;
 	inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
 	inode->i_op = &zonefs_dir_inode_operations;
@@ -1371,6 +1857,8 @@ static void zonefs_kill_super(struct super_block *sb)
 
 	if (sb->s_root)
 		d_genocide(sb->s_root);
+
+	zonefs_sysfs_unregister(sb);
 	kill_block_super(sb);
 	kfree(sbi);
 }
@@ -1418,16 +1906,26 @@ static int __init zonefs_init(void)
 		return ret;
 
 	ret = register_filesystem(&zonefs_type);
-	if (ret) {
-		zonefs_destroy_inodecache();
-		return ret;
-	}
+	if (ret)
+		goto destroy_inodecache;
+
+	ret = zonefs_sysfs_init();
+	if (ret)
+		goto unregister_fs;
 
 	return 0;
+
+unregister_fs:
+	unregister_filesystem(&zonefs_type);
+destroy_inodecache:
+	zonefs_destroy_inodecache();
+
+	return ret;
 }
 
 static void __exit zonefs_exit(void)
 {
+	zonefs_sysfs_exit();
 	zonefs_destroy_inodecache();
 	unregister_filesystem(&zonefs_type);
 }
@@ -1435,5 +1933,6 @@ static void __exit zonefs_exit(void)
 MODULE_AUTHOR("Damien Le Moal");
 MODULE_DESCRIPTION("Zone file system for zoned block devices");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_FS("zonefs");
 module_init(zonefs_init);
 module_exit(zonefs_exit);